DAVE：一种强制使用策略的LLM发言人，用于安全的多文档数据共享
DAVE: A Policy-Enforcing LLM Spokesperson for Secure Multi-Document Data Sharing
AI总结：
DAVE是一种强制使用策略的LLM发言人，通过自然语言接口在不泄露敏感信息的情况下实现安全的多文档数据共享。
摘要：
在当前的跨组织数据空间中，使用策略主要是在资产层面执行：一个完整的文档或数据集要么被共享要么被拒绝。当仅文档的一部分敏感时，希望避免泄露受保护信息的提供者通常必须手动对文档进行脱敏处理后再进行共享，这成本高、粒度粗且难以维护，因为策略或合作伙伴发生变化。我们提出了DAVE，一种强制使用策略的LLM发言人，代表数据提供者回答关于私有文档的问题。不是释放文档，提供者暴露一个自然语言接口，其响应受机器可读的使用策略所限制。我们在此设定中正式化了违反策略的信息泄露，借鉴了使用控制和信息流安全，并引入了虚拟脱敏：在查询时抑制敏感信息而不修改源文档。我们描述了一种将此类发言人与Eclipse Dataspace Components和ODRL风格策略集成的架构，并概述了一个初始的提供方侧集成原型，其中QA请求通过发言人服务路由而不是触发原始文档传输。我们的贡献主要是架构方面的：我们尚未实现或经验性评估完整的执行流程。因此，我们概述了评估方法论，以评估在良性和对抗性查询下的安全、实用性和性能权衡，作为未来系统性管理LLM访问多方数据空间的实证工作的基础。
英文摘要：
In current inter-organizational data spaces, usage policies are enforced mainly at the asset level: a whole document or dataset is either shared or withheld. When only parts of a document are sensitive, providers who want to avoid leaking protected information typically must manually redact documents before sharing them, which is costly, coarse-grained, and hard to maintain as policies or partners change. We present DAVE, a usage policy-enforcing LLM spokesperson that answers questions over private documents on behalf of a data provider. Instead of releasing documents, the provider exposes a natural language interface whose responses are constrained by machine-readable usage policies. We formalize policy-violating information disclosure in this setting, drawing on usage control and information flow security, and introduce virtual redaction: suppressing sensitive information at query time without modifying source documents. We describe an architecture for integrating such a spokesperson with Eclipse Dataspace Components and ODRL-style policies, and outline an initial provider-side integration prototype in which QA requests are routed through a spokesperson service instead of triggering raw document transfer. Our contribution is primarily architectural: we do not yet implement or empirically evaluate the full enforcement pipeline. We therefore outline an evaluation methodology to assess security, utility, and performance trade-offs under benign and adversarial querying as a basis for future empirical work on systematically governed LLM access to multi-party data spaces.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
